Addressing Spatial Indistinguishability in Spatiotemporal Prediction via Optimal Transport-Guided Masking
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Discrete Graph Structure Learning for Forecasting Multiple Time Series
- Dynamic Frequency Domain Graph Convolutional Network for Traffic Forecasting
- ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- Ti-MAE: Self-Supervised Masked Time Series Autoencoders
- Learning to Embed Time Series Patches Independently
- A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks